Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to structure or format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pymongo
    -0.51
    TAWA
    -0.48
     CURIAM
    -0.48
     estekak
    -0.43
     remont
    -0.43
    findpost
    -0.41
    cla
    -0.40
    (&:
    -0.40
    western
    -0.40
    日閲覧
    -0.40
    POSITIVE LOGITS
    (!__
    0.69
    addCriterion
    0.66
     faveur
    0.61
     parlant
    0.61
    TestingModule
    0.59
     avoient
    0.59
    ContentAsync
    0.58
     AssemblyProduct
    0.58
     ThemeData
    0.57
     sauvages
    0.57
    Act Density 0.004%

    No Known Activations